First-order and Stochastic Optimization Methods for Machine Learning

452 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Superquantile Approach to Federated Learning with Heterogeneous Devices (2021, background): “Lemma 2 ensures that ψ t is L w -smooth and λ -strongly convex which in turn yields [14]: Let F t denote the σ -algebra generated by w t .”
Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms (2020, methodology): “Moreover, the value of r boils down to r = max Consider the applications of SGD covered by Assumption 1, and mentioned in Sect.”